Illumio MCP Server

get-traffic-timeline

Generate a time-bucketed flow and connection count timeline from a single Explorer query, including zero-count buckets, to chart blocked traffic per hour or day.

Instructions

Time-bucketed flow counts from ONE Explorer query: how many flows and connections fell into each 15m/1h/6h/1d bucket of the window, with every bucket present (zeros included). Use it for 'blocked flows per hour for app X' instead of one summary query per bucket. Rows are bucketed by first_detected; Explorer aggregates a persistent connection (and, for older data, several days) into one row, so rows_spanning_buckets and resolution_note say how much the start of the window is smeared. spikes=true applies the shared rule: a bucket >= 3x the median of the non-zero buckets is a spike, and worst names the largest with its multiple.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get-traffic-timeline"
  }
}

Input Schema

Name	Required	Description
`bucket`	No	Bucket size (default 1h). Buckets align to the wall clock, not the window start. Max 2000 buckets.
`spikes`	No	Add `spikes`: median of non-zero buckets, threshold (3x), the buckets above it and the worst one
`end_date`	No	YYYY-MM-DD or ISO-8601 timestamp; defaults to today
`split_by`	No	Add a per-bucket breakdown: by_policy_decision or by_flow_direction
`query_name`	No
`start_date`	No	YYYY-MM-DD or ISO-8601 timestamp; defaults to lookback_days ago
`max_results`	No	Query cap (default 200000); counts are lower bounds when hit
`lookback_days`	No	Used when start_date is omitted (default 1)
`exclude_sources`	No	Sources to exclude
`include_sources`	No	Sources to include: label HREFs or key=value (entries are ANDed), IP list/workload HREFs, IPs. FQDNs are destination-only
`exclude_services`	No
`include_services`	No
`policy_decisions`	No	e.g. ['blocked'] for a blocked-flow timeline
`exclude_destinations`	No	Destinations to exclude
`include_destinations`	No	Destinations to include, same forms as include_sources plus FQDNs and broadcast/multicast/unicast
`exclude_workloads_from_ip_list_query`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.13.0Oct 31, 2026

changedInput schema / properties / include_destinations / description

Previous value: -"Destinations to include, same forms as include_sources"New value: +"Destinations to include, same forms as include_sources plus FQDNs and broadcast/multicast/unicast"

changedInput schema / properties / include_sources / description

Previous value: -"Sources to include: label HREFs or key=value (entries are ANDed), IP list/workload HREFs, FQDNs, IPs"New value: +"Sources to include: label HREFs or key=value (entries are ANDed), IP list/workload HREFs, IPs. FQDNs are destination-only"

Addedv0.11.0Oct 14, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does it well: it explains bucketing by first_detected, that persistent connections smear across buckets, that rows_spanning_buckets/resolution_note quantify the smear, that counts become lower bounds at max_results, and the exact spike rule (>=3x median of non-zero buckets, worst multiple).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, front-loaded with the core purpose and the alternative-avoidance hint before the caveats. Some sentences are dense (the first_detected smearing clause), but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 16-parameter tool with no annotations and no output schema, the description covers the key return concepts (bucket fields, rows_spanning_buckets, resolution_note, spikes/worst) and the main caveats. The filter parameters are only covered by schema, which is acceptable but leaves minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, so the schema already documents many params; the description adds real semantics beyond it by explaining the spike threshold computation and the lower-bound behavior of max_results, though it leaves the include/exclude filter families entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource+scope: 'Time-bucketed flow counts from ONE Explorer query', and immediately specifies the four bucket sizes and zero-filling. An agent can distinguish this from summary/flow-list siblings without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete use case ('blocked flows per hour for app X') and explains why not to loop a summary query per bucket, which implicitly steers away from get-traffic-flows-summary. It never names sibling tools explicitly or states when-not to use it, keeping it short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server